Multi-modal graph reasoning for structured video text extraction.

Weitao Shi Han Wang Xin Lou

Published in: Comput. Electr. Eng. (2023)

Keyphrases

multi modal
text extraction
video search
multiple modalities
video data
video sequences
video content
multimedia
video frames
complex background
text processing
text segmentation
natural scenes
connected components
video images
text information
image annotation
key frames
image classification
high level